LLM Deployment Engineer

LLM Deployment Engineer

Destinus · Zürich, Switzerland (Hybrid) · Full-time · Posted 2026-11-04

Workplace: hybrid

Department: Machine Learning & Software Engineering

Description

About the role

We are seeking an LLM Deployment Engineer to drive the adoption of AI-powered automation across the organization. In this role, you will deploy and scale LLMs to streamline business processes and assist engineering R&D.

You'll work at the intersection of ML, software infrastructure engineering, and enterprise systems, by developing integration and automation solutions that enable teams across the organization to operate more efficiently.

What You´ll Do

· Deploy and maintain open-weights LLMs on cloud and local cluster.

· Scale deployments to serve a large number of users within the organization.

· Be up-to-date with new model releases, to keep our deployment state of the art.

· Connect LLMs to specific use cases, helping users across the organization to automate their work routine.

· Analyze the effectiveness of models on automation tasks.

· Embed security and privacy in the automation pipeline, to safeguard sensitive content.

Requirements

What You’ll Need

· 3+ years of professional experience in software engineering

· Experience working with LLM APIs, both open-weight and proprietary

· Familiarity with LLM applications, including tools, retrieval-augmented generation (RAG) and routing

· Experience with CI/CD pipelines, infrastructure as code, and modern software delivery practices

· Understanding of security and privacy considerations in enterprise environments

· Strong problem-solving skills and the ability to collaborate effectively across technical and non-technical teams

**Nice to have

**· Knowledge of Model Context Protocol (MCP) or similar interoperability standards

· Experience with AI governance, observability, or operational monitoring

· Proficiency with cloud platforms (AWS, GCP, or Azure), and high-performance computing environments (Kubernetes, SLURM).

· Experience in evaluating ML models.

Who You Are

You thrive in fast-paced environments where ambiguity is part of the challenge, and you can turn it into defined goals. You take ownership seriously and move things forward without waiting for perfect conditions. You know how to balance structure with flexibility without losing focus. Above all, you measure success by outcomes and take pride in getting things done.

Apply

Apply at Destinus

---

Powered by Workable